ICML 2025 论文列表

We propose a data-driven approach to analyzing query complexity in Video Question Answering (VideoQA). Previous efforts in benchmark design have relied on human expertise to design challenging questions, yet we experimentally show that humans struggle to predict which questions are difficult for machine learning models. Our automatic approach leverages recent advances in code generation for visual question answering, using the complexity of generated code as a proxy for question difficulty. We demonstrate that this measure correlates significantly better with model performance than human estimates. To operationalize this insight, we propose an algorithm for estimating question complexity from code. It identifies fine-grained primitives that correlate with the hardest questions for any given set of models, making it easy to scale to new approaches in the future. Finally, to further illustrate the utility of our method, we extend it to automatically generate complex questions, constructing a new benchmark that is 1.9 times harder than the popular NExT-QA.

Large Language Models (LLMs) have revolutionized various natural language processing tasks with their remarkable capabilities. However, challenges persist in effectively integrating new knowledge into LLMs without compromising their performance, particularly in the Large Language Models (LLMs) have revolutionized various natural language processing tasks with their remarkable capabilities. However, a challenge persists in effectively processing new information, particularly in the area of long-term knowledge updates without compromising model performance. To address this challenge, this paper introduces a novel memory augmentation framework that conceptualizes memory as a peripheral component (akin to physical RAM), with the LLM serving as the information processor (analogous to a CPU). Drawing inspiration from RAM architecture, we design memory as a sequence of memory banks, each modeled using Kolmogorov-Arnold Network (KAN) to ensure smooth state transitions. Memory read and write operations are dynamically controlled by query signals derived from the LLMs' internal states, closely mimicking the interaction between a CPU and RAM. Furthermore, a dedicated memory bank is used to generate a mask value that indicates the relevance of the retrieved data, inspired by the sign bit in binary coding schemes. The retrieved memory feature is then integrated as a prefix to enhance the model prediction. Extensive experiments on knowledge-based model editing validate the effectiveness and efficiency of our peripheral memory.

Despite the remarkable performance of Large Language Models (\textbf{LLMs}), they remain vulnerable to jailbreak attacks, which can compromise their safety mechanisms. Existing studies often rely on brute-force optimization or manual design, failing to uncover potential risks in real-world scenarios. To address this, we propose a novel jailbreak attack framework, \textbf{ICRT}, inspired by heuristics and biases in human cognition. Leveraging the \textit{simplicity effect}, we employ \textit{cognitive decomposition} to reduce the complexity of malicious prompts. Simultaneously, \textit{relevance bias} is utilized to reorganize prompts, enhancing semantic alignment and inducing harmful outputs effectively. Furthermore, we introduce a ranking-based harmfulness evaluation metric that surpasses the traditional binary success-or-failure paradigm by employing ranking aggregation methods such as Elo, HodgeRank, and Rank Centrality to comprehensively quantify the harmfulness of generated content. Experimental results show that our approach consistently bypasses mainstream \textbf{LLMs}' safety mechanisms and generates high-risk content.

We introduce Adjoint Sampling, a highly scalable and efficient algorithm for learning diffusion processes that sample from unnormalized densities, or energy functions. It is the first on-policy approach that allows significantly more gradient updates than the number of energy evaluations and model samples, allowing us to scale to much larger problem settings than previously explored by similar methods. Our framework is theoretically grounded in stochastic optimal control and shares the same theoretical guarantees as Adjoint Matching, being able to train without the need for corrective measures that push samples towards the target distribution. We show how to incorporate key symmetries, as well as periodic boundary conditions, for modeling molecules in both cartesian and torsional coordinates. We demonstrate the effectiveness of our approach through extensive experiments on classical energy functions, and further scale up to neural network-based energy models where we perform amortized conformer generation across many molecular systems. To encourage further research in developing highly scalable sampling methods, we plan to open source these challenging benchmarks, where successful methods can directly impact progress in computational chemistry. Code \& and benchmarks provided at https://github.com/facebookresearch/adjoint_sampling.

Modern machine learning applications are characterized by the increasing size of deep models and the growing diversity of data modalities. This trend underscores the importance of efficiently adapting pre-trained multi-modal models to the test distribution in real time, i.e., multi-modal test-time adaptation. In practice, the magnitudes of multi-modal shifts vary because multiple data sources interact with the impact factor in diverse manners. In this research, we investigate the the under-explored practical scenario *uni-modal distribution shift*, where the distribution shift influences only one modality, leaving the others unchanged. Through theoretical and empirical analyses, we demonstrate that the presence of such shift impedes multi-modal fusion and leads to the negative transfer phenomenon in existing test-time adaptation techniques. To flexibly combat this unique shift, we propose a selective adaptation schema that incorporates multiple modality-specific adapters to accommodate potential shifts and a ``router'' module that determines which modality requires adaptation. Finally, we validate the effectiveness of our proposed method through extensive experimental evaluations. Code available at https://github.com/chenmc1996/Uni-Modal-Distribution-Shift.

We address the problem of predicting the next states of a dynamical system governed by *unknown* temporal partial differential equations (PDEs) using only a short trajectory. While standard transformers provide a natural black-box solution to this task, the presence of a well-structured evolution operator in the data suggests a more tailored and efficient approach. Specifically, when the PDE is fully known, classical numerical solvers can evolve the state accurately with only a few parameters. Building on this observation, we introduce DISCO, a model that uses a large hypernetwork to process a short trajectory and generate the parameters of a much smaller operator network, which then predicts the next states through time integration. Our framework decouples dynamics estimation -- i.e., DISCovering an evolution Operator from a short trajectory -- from state prediction -- i.e., evolving this operator. Experiments show that pretraining our model on diverse physics datasets achieves state-of-the-art performance while requiring significantly fewer epochs. Moreover, it generalizes well to unseen initial conditions and remains competitive when fine-tuned on downstream tasks.

Recent advances toward foundation models for routing problems have shown great potential of a unified deep model for various VRP variants. However, they overlook the complex real-world customer distributions. In this work, we advance the Multi-Task VRP (MTVRP) setting to the more realistic yet challenging Multi-Task Multi-Distribution VRP (MTMDVRP) setting, and introduce SHIELD, a novel model that leverages both *sparsity* and *hierarchy* principles. Building on a deeper decoder architecture, we first incorporate the Mixture-of-Depths (MoD) technique to enforce sparsity. This improves both efficiency and generalization by allowing the model to dynamically select nodes to use or skip each decoder layer, providing the needed capacity to adaptively allocate computation for learning the task/distribution specific and shared representations. We also develop a context-based clustering layer that exploits the presence of hierarchical structures in the problems to produce better local representations. These two designs inductively bias the network to identify key features that are common across tasks and distributions, leading to significantly improved generalization on unseen ones. Our empirical results demonstrate the superiority of our approach over existing methods on 9 real-world maps with 16 VRP variants each.

Despite their success in specific scenarios, existing foundation agents still struggle to generalize across various virtual scenarios, mainly due to the dramatically different encapsulations of environments with manually designed observation and action spaces. To handle this issue, we propose the General Computer Control (GCC) setting to restrict foundation agents to interact with software through the most unified and standardized interface, i.e., using screenshots as input and keyboard and mouse actions as output. We introduce Cradle, a modular and flexible LMM-powered framework, as a preliminary attempt towards GCC. Enhanced by six key modules, Information Gathering, Self-Reflection, Task Inference, Skill Curation, Action Planning, and Memory, Cradle is able to understand input screenshots and output executable code for low-level keyboard and mouse control after high-level planning and information retrieval, so that Cradle can interact with any software and complete long-horizon complex tasks without relying on any built-in APIs. Experimental results show that Cradle exhibits remarkable generalizability and impressive performance across four previously unexplored commercial video games (Red Dead Redemption 2, Cities:Skylines, Stardew Valley and Dealer's Life 2), five software applications (Chrome, Outlook, Feishu, Meitu and CapCut), and a comprehensive benchmark, OSWorld. With a unified interface to interact with any software, Cradle greatly extends the reach of foundation agents thus paving the way for generalist agents.

Hierarchical clustering is a widely used method for unsupervised learning with numerous applications. However, in the application of modern algorithms, the datasets studied are usually large and dynamic. If the hierarchical clustering is sensitive to small perturbations of the dataset, the usability of the algorithm will be greatly reduced. In this paper, we focus on the hierarchical $k$ -median clustering problem, which bridges hierarchical and centroid-based clustering while offering theoretical appeal, practical utility, and improved interpretability. We analyze the average sensitivity of algorithms for this problem by measuring the expected change in the output when a random data point is deleted. We propose an efficient algorithm for hierarchical $k$-median clustering and theoretically prove its low average sensitivity and high clustering quality. Additionally, we show that single linkage clustering and a deterministic variant of the CLNSS algorithm exhibit high average sensitivity, making them less stable. Finally, we validate the robustness and effectiveness of our algorithm through experiments.

Label distribution learning (LDL) is a powerful learning paradigm that emulates label polysemy by assigning label distributions over the label space. However, existing LDL evaluation metrics struggle to capture meaningful performance differences due to their insensitivity to subtle distributional changes, and existing LDL learning objectives often exhibit biases by disproportionately emphasizing a small subset of samples with extreme predictions. As a result, the LDL metrics lose their discriminability, and the LDL objectives are also at risk of overfitting. In this paper, we propose DeltaLDL, a percentage of predictions that are approximately correct within the context of LDL, as a solution to the above problems. DeltaLDL can serve as a novel evaluation metric, which is parameter-free and reflects more on real performance improvements. DeltaLDL can also serve as a novel learning objective, which is differentiable and encourages most samples to be predicted as approximately correct, thereby mitigating overfitting. Our theoretical analysis and empirical results demonstrate the effectiveness of the proposed solution.

Diffusion policies have achieved superior performance in imitation learning and offline reinforcement learning (RL) due to their rich expressiveness. However, the conventional diffusion training procedure requires samples from target distribution, which is impossible in online RL since we cannot sample from the optimal policy. Backpropagating policy gradient through the diffusion process incurs huge computational costs and instability, thus being expensive and not scalable. To enable efficient training of diffusion policies in online RL, we generalize the conventional denoising score matching by reweighting the loss function. The resulting Reweighted Score Matching (RSM) preserves the optimal solution and low computational cost of denoising score matching, while eliminating the need to sample from the target distribution and allowing learning to optimize value functions. We introduce two tractable reweighted loss functions to solve two commonly used policy optimization problems, policy mirror descent and max-entropy policy, resulting in two practical algorithms named Diffusion Policy Mirror Descent (DPMD) and Soft Diffusion Actor-Critic (SDAC). We conducted comprehensive comparisons on MuJoCo benchmarks. The empirical results show that the proposed algorithms outperform recent diffusion-policy online RLs on most tasks, and the DPMD improves more than 120% over soft actor-critic on Humanoid and Ant.

In recent years, the pursuit of higher expressive power in graph neural networks (GNNs) has often led to more complex aggregation mechanisms and deeper architectures. To address these issues, we have identified redundant structures in GNNs, and by pruning them, we propose Pruned MP-GNNs, K-Path GNNs, and K-Hop GNNs based on their original architectures. We show that 1) Although some structures are pruned in Pruned MP-GNNs and Pruned K-Path GNNs, their expressive power has not been compromised. 2) K-Hop MP-GNNs and their pruned architecture exhibit equivalent expressiveness on regular and strongly regular graphs. 3) The complexity of pruned K-Path GNNs and pruned K-Hop GNNs is lower than that of MP-GNNs, yet their expressive power is higher. Experimental results validate our refinements, demonstrating competitive performance across benchmark datasets with improved efficiency.

Deep State Space Models (SSMs), such as Mamba (Gu & Dao, 2024), have become powerful tools for language modeling, offering high performance and linear scalability with sequence length. However, the application of parameter-efficient fine-tuning (PEFT) methods to SSM-based models remains largely underexplored. We start by investigating two fundamental questions on existing PEFT methods: (i) How do they perform on SSM-based models? (ii) Which parameters should they target for optimal results? Our analysis shows that LoRA and its variants consistently outperform all other PEFT methods. While LoRA is effective for linear projection matrices, it fails on SSM modules—yet still outperforms other methods applicable to SSMs, indicating their limitations. This underscores the need for a specialized SSM tuning approach. To address this, we propose Sparse Dimension Tuning (SDT), a PEFT method tailored for SSM modules. Combining SDT for SSMs with LoRA for linear projection matrices, we achieve state-of-the-art performance across extensive experiments.

The growing demand for personalized learning underscores the importance of accurately predicting students' future performance to support tailored education and optimize instructional strategies. Traditional approaches predominantly focus on temporal modeling using historical response records and learning trajectories. While effective, these methods often fall short in capturing the intricate interactions between students and learning content, as well as the subtle semantics of these interactions. To address these gaps, we present EduLLM, the first framework to leverage large language models in combination with hypergraph learning for student performance prediction. The framework incorporates FraS-HNN ($\underline{\mbox{Fra}}$melet-based $\underline{\mbox{S}}$igned $\underline{\mbox{H}}$ypergraph $\underline{\mbox{N}}$eural $\underline{\mbox{N}}$etworks), a novel spectral-based model for signed hypergraph learning, designed to model interactions between students and multiple-choice questions. In this setup, students and questions are represented as nodes, while response records are encoded as positive and negative signed hyperedges, effectively capturing both structural and semantic intricacies of personalized learning behaviors. FraS-HNN employs framelet-based low-pass and high-pass filters to extract multi-frequency features. EduLLM integrates fine-grained semantic features derived from LLMs, synergizing with signed hypergraph representations to enhance prediction accuracy. Extensive experiments conducted on multiple educational datasets demonstrate that EduLLM significantly outperforms state-of-the-art baselines, validating the novel integration of LLMs with FraS-HNN for signed hypergraph learning.

Hierarchical classification offers an approach to incorporate the concept of mistake severity by leveraging a structured, labeled hierarchy. However, decoding in such settings frequently relies on heuristic decision rules, which may not align with task-specific evaluation metrics. In this work, we propose a framework for the optimal decoding of an output probability distribution with respect to a target metric. We derive optimal decision rules for increasingly complex prediction settings, providing universal algorithms when candidates are limited to the set of nodes. In the most general case of predicting a *subset of nodes*, we focus on rules dedicated to the hierarchical $\mathrm{hF}_{\beta}$ scores, tailored to hierarchical settings. To demonstrate the practical utility of our approach, we conduct extensive empirical evaluations, showcasing the superiority of our proposed optimal strategies, particularly in underdetermined scenarios. These results highlight the potential of our methods to enhance the performance and reliability of hierarchical classifiers in real-world applications.

Neural scaling laws have garnered significant interest due to their ability to predict model performance as a function of increasing parameters, data, and compute. In this work, we propose a simple statistical ansatz based on memorization to study scaling laws in the context of inference. Specifically, how performance improves with multiple inference attempts. We explore the coverage, or pass@k metric, which measures the chance of success over repeated attempts and provide a motivation for the observed functional form of the inference scaling behavior of the coverage in large language models (LLMs) on reasoning tasks. We then define an "inference loss", which exhibits a power law decay as the number of trials increases, and connect this result with prompting costs. We further test the universality of our construction by conducting experiments on a simple generative model, and find that our predictions are in agreement with the empirical coverage curves in a controlled setting. Our simple framework sets the ground for incorporating inference scaling with other known scaling laws.

Online distributed optimization is particularly useful for solving optimization problems with streaming data collected by multiple agents over a network. When the solutions lie on a Riemannian manifold, such problems become challenging to solve, particularly when efficiency and continuous adaptation are required. This work tackles these challenges and devises a diffusion adaptation strategy for decentralized optimization over general manifolds. A theoretical analysis shows that the proposed algorithm is able to approach network agreement after sufficient iterations, which allows a non-asymptotic convergence result to be derived. We apply the algorithm to the online decentralized principal component analysis problem and Gaussian mixture model inference. Experimental results with both synthetic and real data illustrate its performance.

The Susceptible-Infected-Susceptible (SIS) model is a widely used model for the spread of information and infectious diseases, particularly non-immunizing ones, on a graph. Given a highly contagious disease, a natural question is how to best vaccinate individuals to minimize the disease's extinction time. While previous works showed that the problem of optimal vaccination is closely linked to the NP-hard *Spectral Radius Minimization* (SRM) problem, they assumed that the graph is known, which is often not the case in practice. In this work, we consider the problem of minimizing the extinction time of an outbreak modeled by an SIS model where the graph on which the disease spreads is unknown and only the infection states of the vertices are observed. To this end, we split the problem into two: learning the graph and determining effective vaccination strategies. We propose a novel inclusion-exclusion-based learning algorithm and, unlike previous approaches, establish its sample complexity for graph recovery. We then detail an optimal algorithm for the SRM problem and prove that its running time is polynomial in the number of vertices for graphs with bounded treewidth. This is complemented by an efficient and effective polynomial-time greedy heuristic for any graph. Finally, we present experiments on synthetic and real-world data that numerically validate our learning and vaccination algorithms.

We consider a setting in which the agent aims to maximize the expected cumulative reward, subject to a constraint that the entropic risk of the total utility exceeds a given threshold. Unlike the risk-neutral case, standard primal-dual approaches fail to directly yield regret and violation bounds, as value iteration with respect to a combined state-action value function is not applicable in the risk-sensitive setting. To address this, we adopt the Optimized Certainty Equivalent (OCE) representation of the entropic risk measure and reformulate the problem by augmenting the state space with a continuous budget variable. We then propose a primal-dual algorithm tailored to this augmented formulation. In contrast to the standard approach for risk-neutral CMDPs, our method incorporates a truncated dual update to account for the possible absence of strong duality. We show that the proposed algorithm achieves regret of $\tilde{\mathcal{O}}\big(V_{g,\max}K^{3/4} + \sqrt{H^4 S^2 A \log(1/\delta)}K^{3/4}\big)$ and constraint violation of $\tilde{\mathcal{O}}\big(V_{g,\max} \sqrt{ {H^3 S^2 A \log(1/\delta)}}K^{3/4} \big)$ with probability at least $1-\delta$, where $S$ and $A$ denote the cardinalities of the state and action spaces, respectively, $H$ is the episode length, $K$ is the number of episodes, $\alpha < 0$ is the risk-aversion parameter, and $V_{g,\max} = \frac{1}{|\alpha|}(\exp(|\alpha|H) - 1)$. *To the best of our knowledge, this is the first result establishing sublinear regret and violation bounds for the risk-sensitive CMDP problem.*